Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/133272
Share/Export:
logo share SHARE logo core CORE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Invite to open peer review
Title

A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron

AuthorsOrtín González, Silvia CSIC ORCID; Soriano, Miguel C. ; Pesquera, Luis CSIC ORCID ; Brunner, Daniel CSIC ORCID; San-Martín, Daniel; Fischer, Ingo CSIC ORCID ; Mirasso, Claudio R. CSIC ORCID ; Gutiérrez, José M. CSIC ORCID
Issue Date2015
PublisherNature Publishing Group
CitationScientific Reports 5: 14945 (2015)
AbstractIn this paper we present a unified framework for extreme learning machines and reservoir computing (echo state networks), which can be physically implemented using a single nonlinear neuron subject to delayed feedback. The reservoir is built within the delay-line, employing a number of virtual neurons. These virtual neurons receive random projections from the input layer containing the information to be processed. One key advantage of this approach is that it can be implemented efficiently in hardware. We show that the reservoir computing implementation, in this case optoelectronic, is also capable to realize extreme learning machines, demonstrating the unified framework for both schemes in software as well as in hardware.
Publisher version (URL)http://dx.doi.org/10.1038/srep14945
URIhttp://hdl.handle.net/10261/133272
DOI10.1038/srep14945
Identifiersissn: 2045-2322
Appears in Collections:(IFISC) Artículos
(IFCA) Artículos




Files in This Item:
File Description SizeFormat
time-delayed_neuron_Ortin.pdf564,58 kBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

PubMed Central
Citations

16
checked on Apr 11, 2024

SCOPUSTM   
Citations

127
checked on Apr 12, 2024

WEB OF SCIENCETM
Citations

116
checked on Feb 27, 2024

Page view(s)

478
checked on Apr 16, 2024

Download(s)

254
checked on Apr 16, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Related articles:


This item is licensed under a Creative Commons License Creative Commons